SALVe: Semantic Alignment Verification for Floorplan Reconstruction from Sparse Panoramas

TL;DR

SALVe introduces a novel pairwise learned alignment verifier for automatic 2D floorplan reconstruction from sparse panoramas, significantly improving completeness over existing SfM systems by leveraging semantic features and pose graph optimization.

Contribution

The paper presents SALVe, a new learned alignment verifier that enhances floorplan reconstruction accuracy and completeness from sparse panoramic data.

Findings

Outperforms state-of-the-art SfM systems in completeness by over 200%.

81% of panoramas localized within the first 2 connected components.

89% of panoramas localized within the first 3 connected components.

Abstract

We propose a new system for automatic 2D floorplan reconstruction that is enabled by SALVe, our novel pairwise learned alignment verifier. The inputs to our system are sparsely located 360$^\circ$ panoramas, whose semantic features (windows, doors, and openings) are inferred and used to hypothesize pairwise room adjacency or overlap. SALVe initializes a pose graph, which is subsequently optimized using GTSAM. Once the room poses are computed, room layouts are inferred using HorizonNet, and the floorplan is constructed by stitching the most confident layout boundaries. We validate our system qualitatively and quantitatively as well as through ablation studies, showing that it outperforms state-of-the-art SfM systems in completeness by over 200%, without sacrificing accuracy. Our results point to the significance of our work: poses of 81% of panoramas are localized in the first 2 connected components (CCs), and 89% in the first 3 CCs. Code and models are publicly available at https://github.com/zillow/salve.